© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 130737
    Prev
    Next
    INDEX
    Explanations

    This neuron fires mainly at sentence boundaries—marking the ends of sentences and the beginnings of the next ones.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    end of sentence or clause

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    อร่อย
    -1.05
     imgs
    -0.98
    endaftar
    -0.98
     ()=>{
    -0.91
    ☀
    -0.89
    estroying
    -0.88
    xl
    -0.88
    也會
    -0.88
     буенча
    -0.88
    可能會
    -0.85
    POSITIVE LOGITS
    Mesmo
    1.30
     similar
    1.13
    ofold
    1.10
    aites
    1.06
     Mesmo
    1.05
     once
    1.03
     deveria
    1.03
     couldn
    1.01
     comparable
    1.01
     not
    0.99
    Activations Density 0.020%

    No Known Activations